ClawHub
Back to skill

Security audit

CCPA Privacy Checker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent CCPA assessment tool that sends user-provided business privacy answers to an external API, with no local execution or persistence found.

Install only if you are comfortable sending the entered business privacy and compliance details to the listed third-party API. Avoid including unnecessary regulated, customer-specific, or confidential records beyond the assessment fields.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly asks users to submit detailed business and privacy-practice information, including categories of personal information, sensitive data handling, third-party sharing, and consumer-rights processes, but it does not warn that this data will be sent to an external third-party API. In a privacy/compliance context, this omission is especially risky because users may disclose regulated or confidential operational details under the assumption the assessment is local or trusted, creating avoidable confidentiality and compliance exposure.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
86% confidence
Finding

The skill references an external API endpoint that will receive the assessment payload, which includes potentially sensitive business compliance and data-governance details. While external APIs are expected for tool skills, the danger arises because the endpoint belongs to a third-party domain and the skill provides no trust, retention, jurisdiction, or handling guarantees for the transmitted information.

Content

Scanner excerpt · SKILL.md (reported line 215)May include surrounding context.

md
## References

- **Kong Route:** https://api.mkkpro.com/compliance/ccpa-privacy
- **API Docs:** https://api.mkkpro.com:8040/docs

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This API collects extensive business and privacy-governance information, including potentially sensitive details about data practices, but the specification provides no user-facing disclosure that these answers will be transmitted to an external service. In a privacy/compliance context, silent transmission is especially risky because users may reasonably assume they are performing a local assessment rather than sending operational privacy data off-platform.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This JSON OpenAPI file defines a callable operation but provides only a generic summary and operationId, without any description of when the skill should or should not be invoked. For manifest-like files, the lack of explicit trigger constraints or negative examples can lead to overly broad or unintended activation by orchestration systems.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.